© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72410
    Prev
    Next
    INDEX
    Explanations

    observations and findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    нью
    -1.20
     minimalis
    -1.20
    kalender
    -1.19
    ystemen
    -1.18
     kanker
    -1.16
    
    -1.15
    ーズン
    -1.14
     öf
    -1.14
     диван
    -1.13
    ftig
    -1.13
    POSITIVE LOGITS
     achieved
    1.85
     found
    1.85
     when
    1.74
     in
    1.54
     observed
    1.36
     thấy
    1.35
    vádz
    1.34
     see
    1.33
     this
    1.33
     seen
    1.29
    Activations Density 0.070%

    No Known Activations